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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    The neuron activates on and thus detects floating‐point numeric literals (numbers with a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    alternate
    -0.06
     machen
    -0.06
     polishing
    -0.06
     functionName
    -0.06
    ilation
    -0.06
    ЎыџNЎыџN
    -0.06
     ecstatic
    -0.06
    �
    -0.06
    ablytyped
    -0.06
    ření
    -0.06
    POSITIVE LOGITS
     гр
    0.07
     faded
    0.07
    'id
    0.06
    .createClass
    0.06
    Validate
    0.06
     gathered
    0.06
    _coordinates
    0.06
     خانم
    0.06
     RECORD
    0.06
    _frames
    0.06
    Act Density 0.062%

    No Known Activations