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

    Neuronpedia

    INDEX
    Explanations

    resistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    grow
    -0.07
     lakes
    -0.07
    izando
    -0.07
     Entries
    -0.06
    uação
    -0.06
    _tokens
    -0.06
     creativity
    -0.06
    Airport
    -0.06
     healthy
    -0.06
    _la
    -0.06
    POSITIVE LOGITS
     き
    0.06
     피
    0.06
     ISIS
    0.06
     provides
    0.06
     queue
    0.06
     Hitler
    0.05
    usra
    0.05
     Modern
    0.05
    ieg
    0.05
    )))↵
    0.05
    Act Density 0.004%

    No Known Activations