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

    Neuronpedia

    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash

    This neuron detects numeric decimal values (especially detailed solubility or similar measurements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .icons
    -0.08
    -0.08
     Brigham
    -0.07
    carousel
    -0.07
     plaint
    -0.06
    implicit
    -0.06
     あ
    -0.06
    erto
    -0.06
    -0.06
    Filter
    -0.06
    POSITIVE LOGITS
    .ex
    0.07
    ルク
    0.07
     okay
    0.07
     후
    0.06
     waypoint
    0.06
     eccentric
    0.06
     nghiệm
    0.06
    _BOX
    0.06
     turbines
    0.06
    ,\↵
    0.06
    Act Density 0.003%

    No Known Activations