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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     INLINE
    -0.07
     або
    -0.06
     thresholds
    -0.06
     BOTTOM
    -0.06
    enefit
    -0.06
     multiline
    -0.06
     Ter
    -0.06
    .token
    -0.06
    _Controller
    -0.06
     downgrade
    -0.06
    POSITIVE LOGITS
     запис
    0.07
     rins
    0.07
    责
    0.07
    (song
    0.07
     зависимости
    0.07
     każ
    0.07
    calc
    0.07
     거야
    0.07
    (auth
    0.06
    iggins
    0.06
    Act Density 0.001%

    No Known Activations