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

    Neuronpedia

    INDEX
    Explanations

    compliance/violation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rita
    -0.06
     subtitle
    -0.06
    dar
    -0.06
     why
    -0.06
    _PHONE
    -0.06
    (te
    -0.06
    ILLA
    -0.06
    Cast
    -0.06
    _PAY
    -0.06
     stir
    -0.06
    POSITIVE LOGITS
    _Server
    0.07
    .";
↵
    0.07
     perpetrated
    0.07
    ongan
    0.07
    =back
    0.07
    撃
    0.06
     léč
    0.06
     expectedResult
    0.06
    _fft
    0.06
     그의
    0.06
    Act Density 0.007%

    No Known Activations