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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dusk
    -0.07
     мали
    -0.07
     теж
    -0.06
    	Map
    -0.06
    @Component
    -0.06
     craft
    -0.06
     signal
    -0.06
    Timeout
    -0.06
     Madd
    -0.06
     نق
    -0.06
    POSITIVE LOGITS
    utivo
    0.06
    fee
    0.06
     Foo
    0.06
     traumat
    0.06
     bother
    0.06
     hormonal
    0.06
     Turing
    0.06
     francais
    0.06
    мець
    0.06
    _Dec
    0.06
    Act Density 0.137%

    No Known Activations