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

    Neuronpedia

    INDEX
    Explanations

    going

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bowel
    -0.07
     Dez
    -0.07
    },{
    -0.07
    ,u
    -0.07
    imensional
    -0.07
     dimensional
    -0.07
    -counter
    -0.07
     Long
    -0.06
    ,O
    -0.06
    cone
    -0.06
    POSITIVE LOGITS
     sacked
    0.07
     radically
    0.07
    앱
    0.07
    กระท
    0.07
    纬
    0.06
    拿到了
    0.06
    HELP
    0.06
    /library
    0.06
    挥手
    0.06
    🛠
    0.06
    Act Density 0.179%

    No Known Activations