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

    Neuronpedia

    INDEX
    Explanations

    deprecated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ему
    -0.07
    stras
    -0.06
     Terminator
    -0.06
    IVERY
    -0.06
     anonymously
    -0.06
    -card
    -0.06
    Password
    -0.06
     jour
    -0.06
    -load
    -0.06
    _HAND
    -0.06
    POSITIVE LOGITS
     yapılır
    0.07
    ENA
    0.07
    (hw
    0.07
    ena
    0.06
    씨
    0.06
     Hoover
    0.06
    وید
    0.06
    ูด
    0.06
     ai
    0.06
    [min
    0.06
    Act Density 0.000%

    No Known Activations