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

    Neuronpedia

    INDEX
    Explanations

    moz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .head
    -0.07
    افته
    -0.07
    нош
    -0.06
     vanished
    -0.06
    aru
    -0.06
    .RequestBody
    -0.06
     информации
    -0.06
     υπάρχουν
    -0.06
     Standards
    -0.06
    비스
    -0.06
    POSITIVE LOGITS
    moz
    0.11
     vodka
    0.08
    oz
    0.07
     oz
    0.07
     moz
    0.07
     ounces
    0.06
    �
    0.06
     Mez
    0.06
     Jeg
    0.06
     shaking
    0.06
    Act Density 0.000%

    No Known Activations