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

    Neuronpedia

    INDEX
    Explanations

    api access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.54
     フル
    0.52
     Familie
    0.51
    .
    0.51
     Lebens
    0.50
     I
    0.50
     Parte
    0.48
     reorgan
    0.48
     Childhood
    0.48
     numar
    0.47
    POSITIVE LOGITS
    le
    0.48
    itives
    0.47
    나
    0.47
    یل
    0.46
     dispel
    0.45
     hovered
    0.45
    istic
    0.44
    zones
    0.43
     canning
    0.43
    नगर
    0.42
    Act Density 0.000%

    No Known Activations