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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (JS
    -0.07
    _X
    -0.07
    Mech
    -0.07
    컴
    -0.07
     stacking
    -0.07
    epoch
    -0.07
     anlamına
    -0.07
    Opt
    -0.07
    .did
    -0.06
    .dt
    -0.06
    POSITIVE LOGITS
    sizei
    0.06
     Nigeria
    0.06
    ')==
    0.06
     ])↵↵
    0.06
     credibility
    0.06
    ละคร
    0.05
     renewables
    0.05
    meyi
    0.05
     слож
    0.05
    οκ
    0.05
    Act Density 0.014%

    No Known Activations