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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron looks for floating-point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     congressional
    -0.07
     dropout
    -0.07
     přib
    -0.07
    IPP
    -0.07
     getClass
    -0.07
     accommodation
    -0.06
    Mary
    -0.06
     None
    -0.06
    ött
    -0.06
    Rows
    -0.06
    POSITIVE LOGITS
    先生
    0.06
    _suffix
    0.06
    τευ
    0.06
    ा:
    0.06
     esse
    0.06
     additive
    0.06
    _lahir
    0.06
    /es
    0.06
     μον
    0.06
    альні
    0.06
    Act Density 0.022%

    No Known Activations