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

    Neuronpedia

    INDEX
    Explanations

    current location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.63
    no
    0.49
    ко
    0.47
    in
    0.46
    true
    0.46
    iname
    0.45
    í
    0.45
     unfl
    0.45
     Л
    0.44
     sì
    0.44
    POSITIVE LOGITS
    ങ്ങാ
    0.48
    리오
    0.47
    cially
    0.46
     Iqbal
    0.45
    .。
    0.44
     മലയാള
    0.44
    广泛
    0.44
     Magi
    0.43
    离
    0.42
     ANS
    0.42
    Act Density 0.001%

    No Known Activations