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

    Neuronpedia

    INDEX
    Explanations

    Basically introducing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਉ
    0.38
    Truthy
    0.35
    Probit
    0.33
    筺
    0.32
    Subtract
    0.32
     działal
    0.32
    asel
    0.32
    筐
    0.31
    یو
    0.31
    IANA
    0.30
    POSITIVE LOGITS
     Basically
    0.52
     basically
    0.43
    basically
    0.43
    Basically
    0.42
     Note
    0.41
     However
    0.41
     básicamente
    0.40
     Creators
    0.39
     Founders
    0.39
     creators
    0.39
    Act Density 0.026%

    No Known Activations