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

    Neuronpedia

    INDEX
    Explanations

    habituation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (proxy
    -0.07
    Hunter
    -0.07
    Cluster
    -0.06
    혀
    -0.06
     lazy
    -0.06
     getter
    -0.06
     Genetic
    -0.06
     Pearl
    -0.06
     Dictionary
    -0.06
    mtx
    -0.06
    POSITIVE LOGITS
     pige
    0.06
     nto
    0.06
     expansions
    0.06
     politik
    0.06
    ักษณะ
    0.06
     OPER
    0.06
    ophysical
    0.06
     slave
    0.06
    /sites
    0.06
    +-+-+-+-+-+-+-+-
    0.06
    Act Density 0.005%

    No Known Activations