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

    Neuronpedia

    INDEX
    Explanations

    to/reply

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Selector
    -0.07
    Viol
    -0.07
     truly
    -0.07
    stan
    -0.07
    .alt
    -0.07
    المع
    -0.07
    .tf
    -0.07
     доп
    -0.07
    CV
    -0.07
    万事
    -0.07
    POSITIVE LOGITS
    全域旅游
    0.07
    зов
    0.07
    ⓔ
    0.06
    ⟰
    0.06
    ('?
    0.06
    �
    0.06
    xbd
    0.06
     phosphate
    0.06
    เธ
    0.06
    乐园
    0.06
    Act Density 0.004%

    No Known Activations