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

    Neuronpedia

    INDEX
    Explanations

    center/centre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SKIP
    -0.07
    uisine
    -0.06
    anoia
    -0.06
     quot
    -0.06
    .dropout
    -0.06
    _token
    -0.06
    uluk
    -0.06
    720
    -0.06
     HOWEVER
    -0.06
    stairs
    -0.06
    POSITIVE LOGITS
     дру
    0.07
     Poz
    0.07
    =center
    0.07
     empez
    0.07
     babys
    0.06
     jailed
    0.06
    jez
    0.06
    Mel
    0.06
     vybav
    0.06
     για
    0.06
    Act Density 0.011%

    No Known Activations