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

    Neuronpedia

    INDEX
    Explanations

    situ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ふ
    -0.07
     Wang
    -0.06
    Instruction
    -0.06
     sentenced
    -0.06
    'h
    -0.06
     Kramer
    -0.06
     ribs
    -0.06
     persuade
    -0.06
     рук
    -0.06
    呼ば
    -0.06
    POSITIVE LOGITS
     applaud
    0.07
    ТО
    0.06
    iedy
    0.06
    (Query
    0.06
    (dynamic
    0.06
     εγκα
    0.06
    jj
    0.06
     $($
    0.06
     países
    0.06
     حزب
    0.06
    Act Density 0.005%

    No Known Activations