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

    Neuronpedia

    INDEX
    Explanations

    Alpine

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “Alpine” (in its various tokenized forms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mappedBy
    -0.07
     fighting
    -0.07
    ydı
    -0.07
     Garcia
    -0.07
     Sal
    -0.07
    Raises
    -0.07
    .easing
    -0.07
    .er
    -0.07
     Messenger
    -0.06
     screams
    -0.06
    POSITIVE LOGITS
     Alpine
    0.11
    pine
    0.09
     Highland
    0.09
     Backup
    0.07
    pf
    0.07
    PS
    0.07
    ्ण
    0.06
    pping
    0.06
    보기
    0.06
    备
    0.06
    Act Density 0.002%

    No Known Activations