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

    Neuronpedia

    INDEX
    Explanations

    Quantifiers

    np_max-act · gemini-2.0-flash

    This neuron fires on statistical or quantitative expressions—i.e. numbers and approximate numeric values (especially decimals and percentages).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ар
    -0.06
    bl
    -0.06
     Arts
    -0.06
     fractures
    -0.06
     Ryder
    -0.06
     valide
    -0.06
    edy
    -0.06
    _MD
    -0.06
     Slots
    -0.06
     MLB
    -0.06
    POSITIVE LOGITS
    reachable
    0.07
    Bài
    0.07
    .↵↵↵↵↵
    0.07
    &);↵↵
    0.06
    ')}}</
    0.06
    ても
    0.06
    \core
    0.06
    _o
    0.06
    .'"↵↵
    0.06
    ___↵↵
    0.06
    Act Density 0.205%

    No Known Activations