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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    moire
    -0.07
    Che
    -0.07
    /current
    -0.07
     Burb
    -0.07
    _buckets
    -0.07
     Che
    -0.07
     اد
    -0.07
    individual
    -0.06
     milk
    -0.06
    ňuje
    -0.06
    POSITIVE LOGITS
     newPos
    0.06
    خل
    0.06
     แต
    0.06
    ])]
    0.06
     }>↵
    0.06
    ducer
    0.06
    есп
    0.06
    (images
    0.06
    ervatives
    0.05
    esto
    0.05
    Act Density 0.028%

    No Known Activations