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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric tokens, especially floating-point numbers and scientific-notation expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	↵	↵	↵	↵
    -0.07
    _fix
    -0.06
    ált
    -0.06
     Fix
    -0.06
    .Access
    -0.06
     Iowa
    -0.06
    _timeline
    -0.06
     evangel
    -0.06
    -google
    -0.06
    .Selection
    -0.06
    POSITIVE LOGITS
    ματο
    0.07
     هد
    0.07
     armored
    0.06
     днів
    0.06
     lugares
    0.06
    ้้
    0.06
    .gridx
    0.06
    0.06
    Descriptors
    0.06
     συμβ
    0.06
    Act Density 0.004%

    No Known Activations