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

    Neuronpedia

    INDEX
    Explanations

    did you know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     harassing
    0.38
    trying
    0.37
     relevante
    0.36
    FINAL
    0.36
    final
    0.36
    solo
    0.34
    จำเป็น
    0.34
    down
    0.34
     relevantes
    0.34
    ಿಕೊಂಡ
    0.34
    POSITIVE LOGITS
    irikan
    0.51
    apatkan
    0.42
    dle
    0.40
    ｛
    0.40
     yöntem
    0.40
     receive
    0.39
    actic
    0.39
    ukung
    0.38
    郦
    0.37
    niej
    0.36
    Act Density 0.001%

    No Known Activations