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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ush
    -0.07
     meetings
    -0.07
     separators
    -0.07
    lying
    -0.07
    yn
    -0.07
    Spinner
    -0.07
     OTHER
    -0.07
    赃
    -0.06
    дум
    -0.06
    告诉我们
    -0.06
    POSITIVE LOGITS
    :add
    0.07
     horizon
    0.07
    펐
    0.07
    _lcd
    0.07
    �
    0.07
    slice
    0.07
    NST
    0.06
    _[
    0.06
     scl
    0.06
    .fromFunction
    0.06
    Act Density 0.022%

    No Known Activations