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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     су
    -0.07
     lan
    -0.07
    (Parameter
    -0.07
     ее
    -0.07
    .FirebaseAuth
    -0.06
     funeral
    -0.06
     Xen
    -0.06
     א
    -0.06
    比例
    -0.06
    cosity
    -0.06
    POSITIVE LOGITS
     FSM
    0.06
    zano
    0.06
    oward
    0.06
     MISSING
    0.06
    ではない
    0.06
     Açık
    0.06
    が
    0.06
    jed
    0.06
     xung
    0.06
    .available
    0.06
    Act Density 0.027%

    No Known Activations