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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pemb
    -0.07
    Serialized
    -0.06
     Prototype
    -0.06
    .NUM
    -0.06
     Wanna
    -0.06
     transform
    -0.06
     трен
    -0.06
    Liter
    -0.06
    _presence
    -0.06
    	PreparedStatement
    -0.06
    POSITIVE LOGITS
    ？”↵↵
    0.07
     onPostExecute
    0.07
     мак
    0.07
     admittedly
    0.07
    ‐‐
    0.07
    *↵↵
    0.07
     громадян
    0.06
    نز
    0.06
    -paying
    0.06
    .…↵↵
    0.06
    Act Density 0.219%

    No Known Activations