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

    Neuronpedia

    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash

    The neuron detects decimal numeric tokens (i.e. numbers with fractional parts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     choking
    -0.07
     cannon
    -0.06
    ]},↵
    -0.06
    ,O
    -0.06
    dec
    -0.06
    ARG
    -0.06
     вибор
    -0.06
     stamina
    -0.06
    ContentLoaded
    -0.06
    _flat
    -0.06
    POSITIVE LOGITS
    νι
    0.07
     stál
    0.07
    erli
    0.07
    ерт
    0.07
     MAKE
    0.06
     COURT
    0.06
    _Blue
    0.06
     느�
    0.06
    物
    0.06
    妙
    0.06
    Act Density 0.090%

    No Known Activations