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

    Neuronpedia

    INDEX
    Explanations

    gender violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आन
    1.31
    Ap
    1.21
    sk
    1.20
     vět
    1.17
     dön
    1.16
     mischiev
    1.16
    gå
    1.16
    Population
    1.16
     Punishment
    1.16
    訖
    1.15
    POSITIVE LOGITS
    屽
    1.32
    язку
    1.18
    संचार
    1.17
    бити
    1.14
    JAVADOC
    1.13
     tired
    1.09
     baik
    1.08
    فهام
    1.08
    -------*/
    1.07
     proven
    1.06
    Act Density 0.000%

    No Known Activations