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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Econom
    -0.08
     Developer
    -0.06
    Retry
    -0.06
    entieth
    -0.06
     Fare
    -0.06
    xl
    -0.06
     Prostit
    -0.06
    fort
    -0.06
     Otto
    -0.06
    .Autowired
    -0.06
    POSITIVE LOGITS
     hatte
    0.07
     checkBox
    0.07
     έχει
    0.06
    ])
↵
↵
    0.06
    	callback
    0.06
    _command
    0.06
     است
    0.06
     STDMETHODCALLTYPE
    0.06
     Deze
    0.06
     ///↵
    0.06
    Act Density 0.001%

    No Known Activations