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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Persona
    -0.07
     فه
    -0.07
    TW
    -0.06
     objectForKey
    -0.06
    								
↵
    -0.06
    pNext
    -0.06
     Accom
    -0.06
     floral
    -0.06
    dismiss
    -0.06
    	ui
    -0.06
    POSITIVE LOGITS
    브
    0.08
    enaire
    0.07
    -alone
    0.07
    ere
    0.06
    циклоп
    0.06
    ector
    0.06
    _ESCAPE
    0.06
    -holder
    0.06
    verity
    0.06
    acters
    0.06
    Act Density 0.021%

    No Known Activations