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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on occurrences of the identifier “object” (e.g. type declarations, casts, and array types using the word “object”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    **↵↵
    -0.07
     textField
    -0.07
     Cardinals
    -0.07
    499
    -0.07
    Light
    -0.07
    ('#
    -0.06
    'h
    -0.06
    "P
    -0.06
     GUIStyle
    -0.06
     UNIX
    -0.06
    POSITIVE LOGITS
    handled
    0.07
     SRC
    0.07
     CSC
    0.07
     δυνα
    0.07
     accom
    0.06
     Pav
    0.06
     Ahmet
    0.06
     پش
    0.06
     tts
    0.06
     एस
    0.06
    Act Density 0.145%

    No Known Activations