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

    Neuronpedia

    INDEX
    Explanations

    Java imports/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '];?>↵
    -0.07
    텐
    -0.07
     derivation
    -0.06
     Merkez
    -0.06
    김
    -0.06
    慶
    -0.06
     якому
    -0.06
     Gest
    -0.06
     Nowadays
    -0.06
    _BT
    -0.06
    POSITIVE LOGITS
     dehydration
    0.08
     că
    0.07
    _cfg
    0.07
    State
    0.07
    _jet
    0.07
     shootout
    0.07
     indigenous
    0.07
     mechanics
    0.07
     solely
    0.06
    idas
    0.06
    Act Density 0.001%

    No Known Activations