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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planet
    -0.07
    este
    -0.07
    LoginPage
    -0.07
     Bay
    -0.07
    る
    -0.06
    ,eg
    -0.06
     retention
    -0.06
     anticipation
    -0.06
    shopping
    -0.06
     Grade
    -0.06
    POSITIVE LOGITS
    _TARGET
    0.07
    첨부
    0.06
     ara
    0.06
    Addresses
    0.06
    *f
    0.06
     чим
    0.06
    »,
    0.06
    όρ
    0.06
     yes
    0.05
     �
    0.05
    Act Density 0.125%

    No Known Activations