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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash

    This neuron detects Android resource identifiers in XML/Java, e.g. tokens like “layout,” “drawable,” “string,” “@,” and “R.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    argar
    -0.06
    صبح
    -0.06
     mend
    -0.06
     FF
    -0.06
    690
    -0.06
     dostan
    -0.06
     merit
    -0.06
     dinheiro
    -0.06
    声音
    -0.06
     Recorder
    -0.06
    POSITIVE LOGITS
     pub
    0.07
    .isValid
    0.07
    .pack
    0.07
    .capacity
    0.06
    ení
    0.06
     toolbox
    0.06
     therap
    0.06
     CRUD
    0.06
    shima
    0.06
    �数
    0.06
    Act Density 0.003%

    No Known Activations