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

    Neuronpedia

    INDEX
    Explanations

    controlling something

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that represent floating-point numeric values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     května
    -0.07
    _VIRTUAL
    -0.07
     NXT
    -0.06
     옷
    -0.06
     Bes
    -0.06
    Cities
    -0.06
     أنه
    -0.06
    erequisites
    -0.06
     тисяч
    -0.06
     просто
    -0.06
    POSITIVE LOGITS
    aden
    0.07
     Brace
    0.07
    ipped
    0.06
    徒歩
    0.06
     unreliable
    0.06
    Vertices
    0.06
    previous
    0.06
     Scala
    0.06
    _back
    0.06
    rone
    0.06
    Act Density 0.050%

    No Known Activations