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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enclave
    -0.07
     devant
    -0.06
     Too
    -0.06
     Hof
    -0.06
    ři
    -0.06
     Boh
    -0.06
     dieser
    -0.06
     valido
    -0.06
     McL
    -0.06
    Il
    -0.06
    POSITIVE LOGITS
     davranış
    0.07
     wave
    0.07
     +#+#+#+#+#+
    0.07
    的事情
    0.06
     FRIEND
    0.06
    的声音
    0.06
     sleek
    0.06
     �
    0.06
     編
    0.06
    RIES
    0.06
    Act Density 0.123%

    No Known Activations