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

    Neuronpedia

    INDEX
    Explanations

    combinations of mathematical symbols and notations

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

    indices and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ec
    -0.53
    laken
    -0.51
     Tric
    -0.50
    grie
    -0.50
    schild
    -0.50
    AISSEE
    -0.49
    asier
    -0.48
     ec
    -0.47
     Ec
    -0.46
     nava
    -0.46
    POSITIVE LOGITS
     numerus
    0.46
    },
    0.45
    },{
    0.42
    :{},
    0.42
    Liefs
    0.42
     kasarigan
    0.42
     pungkas
    0.42
    altezza
    0.40
     Comprometido
    0.40
     Letras
    0.40
    Act Density 0.386%

    No Known Activations