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

    Neuronpedia

    INDEX
    Explanations

    company culture/strategy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .compose
    -0.08
    getPosition
    -0.08
     Dee
    -0.07
     queries
    -0.07
    .compute
    -0.06
     tactics
    -0.06
     vitae
    -0.06
     Griffith
    -0.06
     treasurer
    -0.06
    Photo
    -0.06
    POSITIVE LOGITS
    agger
    0.06
     Agility
    0.06
     demol
    0.06
    aghan
    0.06
    無料
    0.06
    orestation
    0.06
    _don
    0.06
     언
    0.06
    032
    0.06
     Geoffrey
    0.06
    Act Density 0.079%

    No Known Activations