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

    Neuronpedia

    INDEX
    Explanations

    description / lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    滹
    0.55
     installers
    0.52
     abbat
    0.52
     Bartholom
    0.52
    姏
    0.51
    鰤
    0.51
     splice
    0.50
     murderers
    0.50
    邙
    0.50
    ებმა
    0.50
    POSITIVE LOGITS
    ch
    0.49
    h
    0.49
     viewing
    0.48
    e
    0.46
     dictionary
    0.46
    iser
    0.46
    gold
    0.45
    dictionary
    0.44
    ird
    0.44
    bor
    0.44
    Act Density 0.001%

    No Known Activations