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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     restricting
    0.70
     Eminent
    0.68
    glb
    0.66
    NOTA
    0.65
    ²/
    0.65
     ໜອງ
    0.65
    aretro
    0.64
     Pools
    0.63
    刧
    0.63
     limiting
    0.61
    POSITIVE LOGITS
    ത്തിനായി
    0.75
     multic
    0.69
    Conversion
    0.67
     lange
    0.63
     StatusCode
    0.63
    enders
    0.63
     minta
    0.63
     নিজেই
    0.62
     Conversion
    0.62
    長い
    0.62
    Act Density 0.007%

    No Known Activations