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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Estimate
    -0.06
     boost
    -0.06
    _zones
    -0.06
    Apollo
    -0.06
     گ
    -0.06
    -pe
    -0.06
    _SC
    -0.06
                                                ↵
    -0.06
    .raises
    -0.06
     Agents
    -0.06
    POSITIVE LOGITS
     LEFT
    0.10
    LEFT
    0.10
     candy
    0.07
    ncmp
    0.06
    imizde
    0.06
    /Typography
    0.06
    'aut
    0.06
    どう
    0.06
     uniq
    0.06
     etraf
    0.06
    Act Density 0.003%

    No Known Activations