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
    .END
    -0.07
    USTER
    -0.07
    Negative
    -0.07
     Orc
    -0.06
    %M
    -0.06
     ignorant
    -0.06
    _=
    -0.06
    INK
    -0.06
     GetAll
    -0.06
    .communic
    -0.06
    POSITIVE LOGITS
    viewport
    0.07
     confronted
    0.06
    followers
    0.06
    避
    0.06
     softer
    0.06
    かに
    0.06
     tốt
    0.06
    ٢
    0.06
    ــــ
    0.06
     bakımından
    0.06
    Act Density 0.007%

    No Known Activations