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

    Neuronpedia

    INDEX
    Explanations

    programming languages/frameworks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dataset
    -0.07
    Javascript
    -0.07
     stranded
    -0.06
    .have
    -0.06
    imde
    -0.06
    lastName
    -0.06
     jedná
    -0.06
    448
    -0.06
    ew
    -0.06
    wanted
    -0.06
    POSITIVE LOGITS
    _ATTACK
    0.07
    _makeConstraints
    0.07
    essel
    0.06
     DISCLAIM
    0.06
     dựng
    0.06
     âm
    0.06
     gobierno
    0.06
    //(
    0.06
    "Oh
    0.06
     全
    0.06
    Act Density 0.029%

    No Known Activations