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

    Neuronpedia

    INDEX
    Explanations

    lex fridman podcast names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಬಹು
    0.43
     Rechte
    0.40
    定制
    0.38
    嬙
    0.38
    ボトル
    0.37
     parete
    0.37
     القمر
    0.37
     silencing
    0.36
    裝置
    0.36
     isol
    0.36
    POSITIVE LOGITS
     podcast
    1.98
     Podcast
    1.78
     podcasts
    1.73
    podcast
    1.69
    Podcast
    1.67
     Podcasts
    1.42
     pod
    1.20
     Pod
    1.05
    Pod
    1.04
    pod
    0.96
    Act Density 0.007%

    No Known Activations