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

    Neuronpedia

    INDEX
    Explanations

    different options

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens and decimal‐formatted numbers (e.g. “3”, “2.3125”, “1.7626953125”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Bell
    -0.07
     Bell
    -0.07
    <Vector
    -0.07
     rebound
    -0.07
     forgotten
    -0.07
     Codes
    -0.07
    %");↵
    -0.06
     Yep
    -0.06
     zat
    -0.06
    ificación
    -0.06
    POSITIVE LOGITS
    .habbo
    0.07
    َان
    0.07
     ingres
    0.06
     офі
    0.06
     striped
    0.06
    rellas
    0.06
    .RE
    0.06
    ğmen
    0.06
     obst
    0.06
     ard
    0.06
    Act Density 0.028%

    No Known Activations