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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conc
    -0.06
     marked
    -0.06
     mush
    -0.06
     Analog
    -0.06
    neath
    -0.06
     Archae
    -0.06
     Hava
    -0.06
     Desert
    -0.06
    ocre
    -0.06
     desert
    -0.06
    POSITIVE LOGITS
    getMessage
    0.07
    irling
    0.07
    ै,
    0.06
    ahl
    0.06
    .fromString
    0.06
    dür
    0.06
     POINTER
    0.06
    یستم
    0.06
    ادث
    0.06
     chlap
    0.06
    Act Density 0.008%

    No Known Activations