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

    Neuronpedia

    INDEX
    Explanations

    adverse/negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Francis
    -0.08
     shack
    -0.07
    enville
    -0.07
    unci
    -0.07
    beth
    -0.07
    Contracts
    -0.07
    Beans
    -0.06
    corlib
    -0.06
     controls
    -0.06
     Threat
    -0.06
    POSITIVE LOGITS
    /ac
    0.07
    .IMAGE
    0.07
     thường
    0.07
     detail
    0.07
     ,↵
    0.07
    alık
    0.07
    _TIME
    0.07
    大树
    0.07
    fbe
    0.07
    .ac
    0.07
    Act Density 0.023%

    No Known Activations