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
    -league
    -0.07
    ⠀⠀
    -0.07
     dagger
    -0.06
     novels
    -0.06
     manga
    -0.06
    	callback
    -0.06
    هل
    -0.06
    овой
    -0.06
    ’en
    -0.06
     berry
    -0.06
    POSITIVE LOGITS
     nikdo
    0.07
    esc
    0.06
    insics
    0.06
     phil
    0.06
    _than
    0.06
     skeptical
    0.06
    _MethodInfo
    0.06
     surprising
    0.06
    eceğiz
    0.06
     arasında
    0.06
    Act Density 0.008%

    No Known Activations