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

    Neuronpedia

    INDEX
    Explanations

    lower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *B
    -0.07
    уска
    -0.07
    yd
    -0.06
    IRA
    -0.06
    Israeli
    -0.06
    波
    -0.06
    ___
    -0.06
    
    -0.06
     antics
    -0.06
    _ELEMENT
    -0.06
    POSITIVE LOGITS
     Developer
    0.07
    .toLowerCase
    0.07
    _over
    0.07
    負
    0.07
    .lower
    0.07
     impressed
    0.06
    .elem
    0.06
     Typically
    0.06
     Purdue
    0.06
     char
    0.06
    Act Density 0.006%

    No Known Activations