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

    Neuronpedia

    INDEX
    Explanations

    queries related to experiences and feelings

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

    see what happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.47
     SDLK
    -0.46
    ंदीखरीदारी
    -0.42
    stdc
    -0.42
    styleType
    -0.41
    httphttps
    -0.41
    jsxFileName
    -0.41
     Wikimedijinoj
    -0.40
    endphp
    -0.39
     ſta
    -0.39
    POSITIVE LOGITS
    pired
    0.54
    /*
    0.44
     ModelExpression
    0.44
    animous
    0.42
     calda
    0.42
    emy
    0.41
    nende
    0.40
    findpost
    0.39
    امن
    0.39
    CUR
    0.39
    Act Density 0.041%

    No Known Activations