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

    Neuronpedia

    INDEX
    Explanations

    47

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric tokens (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stamped
    -0.07
    experience
    -0.07
    อลลาร
    -0.07
    (scan
    -0.07
    .unique
    -0.07
    "S
    -0.07
    -direction
    -0.07
    .П
    -0.07
    those
    -0.07
    Nice
    -0.06
    POSITIVE LOGITS
    187
    0.06
    voir
    0.06
    wall
    0.06
     Variables
    0.06
     bên
    0.06
     Bruins
    0.06
    expr
    0.05
     Games
    0.05
    _decl
    0.05
     [],
↵
    0.05
    Act Density 0.003%

    No Known Activations