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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lineman
    -0.07
    system
    -0.06
     novel
    -0.06
    _layers
    -0.06
     Madison
    -0.06
    Manchester
    -0.06
    ț
    -0.06
    546
    -0.06
     utilizing
    -0.06
    +$
    -0.06
    POSITIVE LOGITS
    ิมพ
    0.07
     perí
    0.07
    aad
    0.07
    Balance
    0.06
     Amph
    0.06
     hora
    0.06
    upp
    0.06
     Аб
    0.06
     Dispatch
    0.06
     창
    0.06
    Act Density 0.051%

    No Known Activations