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

    Neuronpedia

    INDEX
    Explanations

    travel plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    फोल
    0.42
     Sebastian
    0.41
     Echin
    0.41
     Muy
    0.38
    akis
    0.38
    Shang
    0.37
    Sebastian
    0.37
     Ehe
    0.37
     Dalib
    0.36
     Hed
    0.36
    POSITIVE LOGITS
    オーク
    0.41
    Number
    0.40
     இல்லை
    0.40
     towers
    0.38
    प्पू
    0.38
    वर्त
    0.37
    தந்திர
    0.37
    续
    0.36
    रेटर
    0.36
    stopwords
    0.36
    Act Density 0.000%

    No Known Activations