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

    Neuronpedia

    INDEX
    Explanations

    head pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tx
    -0.08
     bufsize
    -0.07
     Prot
    -0.07
    Tx
    -0.07
    virt
    -0.07
    짜
    -0.06
     тут
    -0.06
     matrimon
    -0.06
    -span
    -0.06
    _Pods
    -0.06
    POSITIVE LOGITS
     disagrees
    0.07
    ежать
    0.07
     во
    0.07
     newPosition
    0.07
    ）（
    0.06
    ;y
    0.06
     inaugur
    0.06
    ).</
    0.06
    /documentation
    0.06
    Во
    0.06
    Act Density 0.012%

    No Known Activations