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

    Neuronpedia

    INDEX
    Explanations

    Support\Facades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    é
    0.63
    í
    0.58
     i
    0.56
     পুনঃ
    0.55
    ovine
    0.53
    ie
    0.52
    iegen
    0.51
    ii
    0.51
     =
    0.50
    iis
    0.50
    POSITIVE LOGITS
    Policy
    0.79
    Animator
    0.77
    Credential
    0.73
    Spider
    0.71
    Tolerance
    0.70
     Tendulkar
    0.70
    Inspection
    0.70
    Следу
    0.70
     malu
    0.70
    Atlas
    0.70
    Act Density 0.000%

    No Known Activations