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

    Neuronpedia

    INDEX
    Explanations

    ham and its uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulations
    0.68
    ig
    0.67
    xw
    0.64
    x
    0.64
    less
    0.61
    laus
    0.61
    ae
    0.61
    aire
    0.61
    aya
    0.60
    𝗷
    0.59
    POSITIVE LOGITS
     elytra
    0.59
    ⎆
    0.59
     lobby
    0.57
    ן
    0.55
     pacientes
    0.54
    </sup>
    0.54
    㬹
    0.54
     icono
    0.54
     "'";
    0.53
    🏩
    0.53
    Act Density 0.001%

    No Known Activations