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

    Neuronpedia

    INDEX
    Explanations

    software features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alliances
    -0.06
     Logic
    -0.06
    .rooms
    -0.06
     degrees
    -0.06
    币
    -0.06
    vio
    -0.06
    erif
    -0.06
    andon
    -0.06
    plate
    -0.06
    ITES
    -0.06
    POSITIVE LOGITS
    .IGNORE
    0.07
    .cols
    0.07
     HttpNotFound
    0.07
     salopes
    0.06
    -called
    0.06
    secured
    0.06
    pf
    0.06
     widen
    0.06
    ).'</
    0.06
     свидетель
    0.06
    Act Density 0.059%

    No Known Activations