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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    äll
    -0.07
     busted
    -0.07
     exploiting
    -0.07
    VERTEX
    -0.07
    اءات
    -0.06
    _ability
    -0.06
    modes
    -0.06
     callee
    -0.06
    quality
    -0.06
    cipher
    -0.06
    POSITIVE LOGITS
     LOT
    0.07
    //------------------------------------------------------------------------------↵↵
    0.06
     cực
    0.06
     messaging
    0.06
    Bucket
    0.06
    _configure
    0.06
    τεί
    0.06
     fossil
    0.06
    're
    0.06
    options
    0.06
    Act Density 0.000%

    No Known Activations