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

    Neuronpedia

    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jorn
    -0.08
     cán
    -0.06
    .wav
    -0.06
    -placeholder
    -0.06
     bene
    -0.06
     ques
    -0.06
    ousel
    -0.06
     moveTo
    -0.06
    baz
    -0.06
    ,"%
    -0.06
    POSITIVE LOGITS
     mysteries
    0.07
     limitation
    0.07
    onomic
    0.07
     salt
    0.07
     DIC
    0.07
    YM
    0.07
    422
    0.07
    ivation
    0.06
     slim
    0.06
    .fast
    0.06
    Act Density 0.002%

    No Known Activations