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

    Neuronpedia

    INDEX
    Explanations

    -direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    陶
    -0.07
     valu
    -0.06
    ovo
    -0.06
    .Strict
    -0.06
     hypocrisy
    -0.06
     tox
    -0.06
    QC
    -0.06
    ーデ
    -0.06
     left
    -0.06
    ruc
    -0.06
    POSITIVE LOGITS
    》↵
    0.07
    (Utils
    0.07
     //////////////////////////////////
    0.06
    (cfg
    0.06
     Brewers
    0.06
     Listening
    0.06
    熊
    0.06
     instrumental
    0.06
    stacles
    0.06
    eds
    0.06
    Act Density 0.002%

    No Known Activations