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

    Neuronpedia

    INDEX
    Explanations

    startup.SMS.potential.concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ile
    0.57
    DF
    0.57
    বৎ
    0.54
    ip
    0.52
    OC
    0.52
    ok
    0.51
    ator
    0.51
    GE
    0.51
    E
    0.51
    uk
    0.51
    POSITIVE LOGITS
     Harn
    0.49
     noodles
    0.47
     vesting
    0.45
     jerseys
    0.44
     jeito
    0.43
    нцип
    0.43
     doable
    0.42
     Alcoholic
    0.42
     hảo
    0.42
     duplo
    0.41
    Act Density 0.008%

    No Known Activations