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

    Neuronpedia

    INDEX
    Explanations

    URLs pointing to resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мене
    0.25
    aisesti
    0.24
     saída
    0.24
     një
    0.24
     trolley
    0.23
     мной
    0.23
     অ্যাপ্লিকেশন
    0.22
    餛
    0.22
     resignation
    0.22
     పాటు
    0.22
    POSITIVE LOGITS
    _
    0.30
    K
    0.30
    -
    0.29
    F
    0.27
    S
    0.27
     for
    0.27
     E
    0.26
     S
    0.25
     K
    0.25
    P
    0.25
    Act Density 0.226%

    No Known Activations