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

    Neuronpedia

    INDEX
    Explanations

    .Collections

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of the Java “Collections” identifier.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    theorem
    -0.06
    -free
    -0.06
     jim
    -0.06
    633
    -0.06
     Ashton
    -0.06
     spectra
    -0.06
     assessment
    -0.06
    friendly
    -0.06
     destructive
    -0.06
     hygiene
    -0.06
    POSITIVE LOGITS
    0.07
    [keys
    0.07
     Updating
    0.07
     {...
    0.07
     _.
    0.06
    ;/*
    0.06
    Το
    0.06
     Arabic
    0.06
     +**************
    0.06
     ohled
    0.06
    Act Density 0.003%

    No Known Activations