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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一点
    -0.07
     celebrated
    -0.06
    180
    -0.06
     Asians
    -0.06
    project
    -0.06
     adventurous
    -0.06
    の
    -0.06
    attle
    -0.06
     defender
    -0.06
    出し
    -0.06
    POSITIVE LOGITS
    �
    0.07
    lette
    0.07
    โทร
    0.07
    DOI
    0.07
    (phone
    0.06
    Ε
    0.06
    quipe
    0.06
     kend
    0.06
    (grammar
    0.06
    zt
    0.06
    Act Density 0.099%

    No Known Activations