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

    Neuronpedia

    INDEX
    Explanations

    proportions and probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .port
    -0.07
    _DIV
    -0.06
    _IW
    -0.06
    審
    -0.06
    hyth
    -0.06
     درجه
    -0.06
     pay
    -0.06
    Pure
    -0.06
     hot
    -0.06
     Carlton
    -0.06
    POSITIVE LOGITS
    ayas
    0.07
     Susan
    0.07
     vbCrLf
    0.07
    	Get
    0.07
     při
    0.06
    552
    0.06
    igm
    0.06
    noinspection
    0.06
     myself
    0.06
     fiance
    0.06
    Act Density 0.104%

    No Known Activations