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

    Neuronpedia

    INDEX
    Explanations

    explaining absence or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prostitute
    0.48
    ণু
    0.47
    ट्यूब
    0.45
    ୈ
    0.44
    ーター
    0.44
    াবু
    0.44
    ின்றனர்
    0.44
    にお
    0.43
     oncology
    0.43
     utilizzando
    0.43
    POSITIVE LOGITS
     for
    0.49
    which
    0.47
     Quir
    0.47
     yang
    0.45
     Over
    0.44
     Lec
    0.43
     Multi
    0.43
     Küh
    0.43
     Emb
    0.42
    +
    0.42
    Act Density 0.015%

    No Known Activations