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

    Neuronpedia

    INDEX
    Explanations

    IM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Za
    -0.07
     KeyError
    -0.07
    KH
    -0.07
     Ry
    -0.07
    .places
    -0.07
     Penis
    -0.07
    řich
    -0.07
    Fx
    -0.07
    /Library
    -0.07
    \":\"
    -0.07
    POSITIVE LOGITS
    (""))↵
    0.06
    	FROM
    0.06
     annotated
    0.06
     "~
    0.06
    IRC
    0.05
     offshore
    0.05
     visitor
    0.05
     trafficking
    0.05
     نتیجه
    0.05
    있는
    0.05
    Act Density 0.001%

    No Known Activations