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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion or belief

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

    "do" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    do/does followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferme
    -0.26
                                   
    -0.26
     lungo
    -0.25
     junto
    -0.25
    }`);
    -0.25
     tambor
    -0.24
     langs
    -0.24
    esModule
    -0.24
     voilà
    -0.24
     ...
    -0.24
    POSITIVE LOGITS
     Geſch
    0.78
     indígen
    0.75
     argint
    0.71
    elemField
    0.68
     increí
    0.68
    ResumeLayout
    0.67
     ſtand
    0.67
     wiſſen
    0.66
    <unused8>
    0.66
    <unused14>
    0.66
    Act Density 0.110%

    No Known Activations