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

    Neuronpedia

    INDEX
    Explanations

    DSM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nasty
    -0.07
     Pump
    -0.07
     KK
    -0.07
     목
    -0.06
     Problem
    -0.06
    Walking
    -0.06
    445
    -0.06
     RFID
    -0.06
     Rabbi
    -0.06
     penis
    -0.06
    POSITIVE LOGITS
    كز
    0.07
    utters
    0.07
     contato
    0.07
    .se
    0.06
    皆
    0.06
    execute
    0.06
     llam
    0.06
     [↵
    0.06
    -bordered
    0.06
    von
    0.06
    Act Density 0.022%

    No Known Activations