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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يو
    -0.07
     藤
    -0.07
    �
    -0.06
    jur
    -0.06
    .NonNull
    -0.06
     Jur
    -0.06
     }:
    -0.06
    Ð
    -0.06
     Yuk
    -0.05
     Schultz
    -0.05
    POSITIVE LOGITS
     mascot
    0.08
     disconnect
    0.07
    _face
    0.07
     rasp
    0.07
    ollow
    0.07
    icast
    0.06
     photos
    0.06
    لت
    0.06
     newPos
    0.06
     chees
    0.06
    Act Density 0.069%

    No Known Activations