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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of command‐line utility names (shell commands) in scripts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Collins
    -0.07
     verwenden
    -0.07
     Auschwitz
    -0.07
     Obr
    -0.07
    iliyor
    -0.07
    ICON
    -0.07
    -breaking
    -0.06
    aticon
    -0.06
    diamond
    -0.06
    arrant
    -0.06
    POSITIVE LOGITS
    '=>['
    0.07
    			 ↵
    0.07
     المملكة
    0.07
    /]
    0.06
     Rag
    0.06
    под
    0.06
    چی
    0.06
     accelerate
    0.06
    =>'
    0.06
    Src
    0.06
    Act Density 0.010%

    No Known Activations