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

    Neuronpedia

    INDEX
    Explanations

    cascade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    イド
    -0.07
     identities
    -0.06
    /board
    -0.06
    adress
    -0.06
     Gut
    -0.06
    swith
    -0.06
     Integral
    -0.06
     unmist
    -0.06
     mů
    -0.06
     मर
    -0.06
    POSITIVE LOGITS
     consolidated
    0.08
    ционный
    0.07
     قتل
    0.07
     covered
    0.07
     CWE
    0.06
    ESH
    0.06
    _EXTENDED
    0.06
    ویزی
    0.06
    .SetText
    0.06
    AXB
    0.06
    Act Density 0.001%

    No Known Activations