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

    Neuronpedia

    INDEX
    Explanations

    Names and locations

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are part of personal names (e.g. individual players’ or coaches’ names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    كور
    -0.06
    Drop
    -0.06
     Rise
    -0.06
     bamb
    -0.06
    peon
    -0.06
     rovněž
    -0.06
    Rs
    -0.06
    ipv
    -0.06
    .SQL
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    NewLabel
    0.08
     Hawkins
    0.07
     excellent
    0.07
     targeted
    0.07
     kostenlose
    0.07
     doit
    0.06
     trouvé
    0.06
     safely
    0.06
     drafted
    0.06
    good
    0.06
    Act Density 0.004%

    No Known Activations