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

    Neuronpedia

    INDEX
    Explanations

    On

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expérience
    -0.07
    orc
    -0.06
     дых
    -0.06
    طبيق
    -0.06
    rances
    -0.06
     Dissertation
    -0.06
     Cry
    -0.06
     cry
    -0.06
    	change
    -0.06
    Statements
    -0.06
    POSITIVE LOGITS
     <=>
    0.07
     výsled
    0.07
    ////////////////////////////////////////////////////////////////////////////
    0.07
     Hans
    0.06
    Ult
    0.06
     Ant
    0.06
    ạp
    0.06
    ुपय
    0.06
     �
    0.06
    -item
    0.06
    Act Density 0.023%

    No Known Activations