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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()',
    -0.07
    ップ
    -0.06
     н
    -0.06
     Fox
    -0.06
    „ط
    -0.06
    سان
    -0.06
     purification
    -0.06
    onis
    -0.06
     south
    -0.06
     Cater
    -0.06
    POSITIVE LOGITS
    люч
    0.06
    _MPI
    0.06
     tyranny
    0.06
    [name
    0.06
    _ray
    0.06
    raid
    0.06
    _pts
    0.06
    -condition
    0.06
     negotiating
    0.06
    Velocity
    0.06
    Act Density 0.000%

    No Known Activations