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

    Neuronpedia

    INDEX
    Explanations

    function purpose and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pp
    0.39
     опо
    0.39
     daño
    0.39
     immobilization
    0.37
     sufr
    0.37
     rien
    0.36
     damage
    0.35
     Posters
    0.35
     bows
    0.35
    keV
    0.34
    POSITIVE LOGITS
    Created
    0.49
     created
    0.40
    created
    0.40
    purpose
    0.39
    模块
    0.39
     purpose
    0.39
    제목
    0.37
    CREATED
    0.37
     Created
    0.37
    Purpose
    0.36
    Act Density 0.005%

    No Known Activations