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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tina
    -0.07
    detail
    -0.06
     minutos
    -0.06
     wounded
    -0.06
     Dover
    -0.06
    ève
    -0.06
     vat
    -0.06
    форт
    -0.06
    ruba
    -0.06
    oppable
    -0.06
    POSITIVE LOGITS
    (cd
    0.07
     behalf
    0.07
    örü
    0.07
    Alloc
    0.07
    (set
    0.07
     keeper
    0.07
     comprised
    0.06
    .semantic
    0.06
    _NONNULL
    0.06
     therefore
    0.06
    Act Density 0.147%

    No Known Activations