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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bl
    -0.06
     pastor
    -0.06
    ////////////////////////////////////////////////////////////////////////
    -0.06
    ασίας
    -0.06
     entail
    -0.06
    Strip
    -0.06
    ToWorld
    -0.05
     resilience
    -0.05
    article
    -0.05
     PARTICULAR
    -0.05
    POSITIVE LOGITS
    ณะ
    0.07
    'nda
    0.07
     Synopsis
    0.07
    -/
    0.07
    _COMMON
    0.07
     Otto
    0.07
    igrationBuilder
    0.07
    aligned
    0.07
     ölüm
    0.06
    alım
    0.06
    Act Density 0.024%

    No Known Activations