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

    Neuronpedia

    INDEX
    Explanations

    alone

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical or quantitative expressions (e.g. doses, concentrations, percentages, measurement values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .REACT
    -0.07
     gal
    -0.07
     Insight
    -0.07
    nak
    -0.06
     pink
    -0.06
     impedance
    -0.06
    chantment
    -0.06
     noct
    -0.06
     加
    -0.06
     Interestingly
    -0.06
    POSITIVE LOGITS
    ίτ
    0.06
    ран
    0.06
    ю
    0.06
    :I
    0.06
     lifelong
    0.06
    .AddSingleton
    0.06
    .Console
    0.06
    oub
    0.06
     frü
    0.06
    -line
    0.06
    Act Density 0.014%

    No Known Activations