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

    Neuronpedia

    INDEX
    Explanations

    atomic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gandhi
    -0.08
     Zn
    -0.08
     Susp
    -0.08
                        ↵
    -0.08
     abrupt
    -0.08
    _suspend
    -0.08
     Miet
    -0.08
     Merr
    -0.08
     Zion
    -0.08
    Zn
    -0.07
    POSITIVE LOGITS
     masculino
    0.09
    skosten
    0.08
    'type
    0.08
    PLICATION
    0.08
     masculina
    0.08
     childs
    0.08
     decomposition
    0.08
    TRACT
    0.07
     정도
    0.07
     contou
    0.07
    Act Density 0.001%

    No Known Activations