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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    791
    -0.07
     zel
    -0.07
    __()
    -0.07
    爵
    -0.07
     convict
    -0.07
     ',',
    -0.07
     варто
    -0.06
    #+
    -0.06
    泣
    -0.06
     ANN
    -0.06
    POSITIVE LOGITS
     Abraham
    0.07
     OCI
    0.06
    agini
    0.06
     esteem
    0.06
     Rebel
    0.06
    _adjust
    0.06
     pert
    0.05
    mysqli
    0.05
    Related
    0.05
    ительства
    0.05
    Act Density 0.058%

    No Known Activations