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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     překvap
    -0.07
     turret
    -0.07
     Failure
    -0.06
     trimest
    -0.06
    是在
    -0.06
    Reuse
    -0.06
    ثير
    -0.06
    _;
↵
    -0.06
    ับผ
    -0.06
     وجه
    -0.06
    POSITIVE LOGITS
    cription
    0.07
    _completed
    0.07
    غن
    0.06
    adal
    0.06
    rir
    0.06
    .Call
    0.06
    asurer
    0.06
    piry
    0.06
    öl
    0.06
     concatenated
    0.06
    Act Density 0.020%

    No Known Activations