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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mejorar
    -0.07
     し
    -0.07
     boost
    -0.07
     refusal
    -0.07
     Nes
    -0.07
     marched
    -0.06
     Leading
    -0.06
     را
    -0.06
     Martinez
    -0.06
     attempts
    -0.06
    POSITIVE LOGITS
    icut
    0.06
     cohorts
    0.06
     Waters
    0.06
    Gs
    0.06
    _STRUCT
    0.06
    ^.
    0.06
     sciences
    0.06
    _SECURITY
    0.06
     Byron
    0.06
    alte
    0.06
    Act Density 0.000%

    No Known Activations