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

    Neuronpedia

    INDEX
    Explanations

    no access to search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Emma
    0.42
     Emma
    0.37
     baj
    0.37
    baj
    0.37
     emo
    0.35
    Baj
    0.35
     EMA
    0.33
    EMI
    0.33
     ateliers
    0.33
    haber
    0.32
    POSITIVE LOGITS
    꼬
    0.36
    Kenny
    0.36
     Ped
    0.35
    Ped
    0.35
    シール
    0.34
    Keith
    0.34
     APPEND
    0.33
     Lau
    0.33
     Kenny
    0.33
    Botan
    0.33
    Act Density 0.011%

    No Known Activations