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

    Neuronpedia

    INDEX
    Explanations

    technical instructions

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing floating-point activation values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _reset
    -0.07
    LI
    -0.07
    Checkpoint
    -0.06
     mirrors
    -0.06
    콜
    -0.06
    .isConnected
    -0.06
    夕
    -0.06
    _sl
    -0.06
     カ
    -0.06
    ny
    -0.06
    POSITIVE LOGITS
    '=>'
    0.08
    ('../../
    0.07
    ync
    0.07
    =ax
    0.07
     هم
    0.07
    LOBAL
    0.07
     χρη
    0.06
     PROVID
    0.06
     δικ
    0.06
     Opcode
    0.06
    Act Density 0.070%

    No Known Activations