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

    Neuronpedia

    INDEX
    Explanations

    Nelson Mandela, Jackie Robinson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.88
    t
    0.83
    i
    0.78
    ↵↵
    0.77
    v
    0.76
     kesk
    0.75
    id
    0.73
    r
    0.71
    ק
    0.70
     jurul
    0.67
    POSITIVE LOGITS
    Pressed
    0.64
     Фургала
    0.61
    textepsilon
    0.60
    ajte
    0.59
    <unused601>
    0.59
    Mord
    0.58
     Виктор
    0.58
    Shivam
    0.58
    Forge
    0.56
    젝트
    0.56
    Act Density 0.001%

    No Known Activations