Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    special formatting characters and syntactical structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related tokens and symbols

    np_acts-logits-general · gemini-2.0-flash

    code, foreign, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.69
    Hochspringen
    -0.60
    afficheront
    -0.60
     незавершена
    -0.60
    `]
    -0.57
    ]--;
    -0.55
    ⚭
    -0.54
    তথ্যসূত্র
    -0.54
     Ibidem
    -0.53
    )....
    -0.53
    POSITIVE LOGITS
     I
    0.55
     We
    0.53
    reportWebVitals
    0.49
     betale
    0.49
     useStyles
    0.49
    kubectl
    0.49
     A
    0.49
     Xunit
    0.48
    stddef
    0.47
    iseks
    0.47
    Act Density 0.820%

    No Known Activations