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

    Neuronpedia

    INDEX
    Explanations

    condensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amen
    -0.09
     рест
    -0.09
    公開
    -0.08
     утверж
    -0.08
     publicly
    -0.08
     publiques
    -0.08
     supervising
    -0.08
     પૂ
    -0.08
    фель
    -0.07
     patriarch
    -0.07
    POSITIVE LOGITS
     warms
    0.10
     warmed
    0.09
     warmth
    0.09
     �
    0.08
    暖
    0.08
     heats
    0.08
     गर्म
    0.08
     Vap
    0.08
    屏
    0.08
     chaleur
    0.07
    Act Density 0.007%

    No Known Activations