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

    Neuronpedia

    INDEX
    Explanations

    website snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     her
    -0.08
     fulfil
    -0.07
     him
    -0.07
     Its
    -0.07
     its
    -0.07
    Its
    -0.07
     us
    -0.07
    applicant
    -0.06
    ��
    -0.06
     whistlebl
    -0.06
    POSITIVE LOGITS
     bla
    0.06
     дво
    0.06
     svaz
    0.06
     Glyph
    0.06
                          ↵
    0.06
     collapses
    0.06
     音
    0.06
     collision
    0.06
    ,↵
    0.06
     силы
    0.06
    Act Density 0.275%

    No Known Activations