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

    Neuronpedia

    INDEX
    Explanations

    ff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    298
    -0.07
    “There
    -0.07
    aku
    -0.07
     lý
    -0.07
     الزر
    -0.07
    Location
    -0.07
     sul
    -0.06
    /location
    -0.06
    Camp
    -0.06
    _tag
    -0.06
    POSITIVE LOGITS
    ff
    0.10
    FF
    0.10
    .ff
    0.08
     FF
    0.07
    dff
    0.07
    IFICATION
    0.06
     lifelong
    0.06
    FS
    0.06
     ff
    0.06
    FFFFFFFF
    0.06
    Act Density 0.007%

    No Known Activations