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

    Neuronpedia

    INDEX
    Explanations

    replacement for dock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    edRight
    0.38
    晶
    0.38
    müşt
    0.36
    ramar
    0.36
    ığında
    0.36
     Ernst
    0.36
     Peninsula
    0.35
     फिज
    0.35
    AreEqual
    0.35
     Conservatory
    0.34
    POSITIVE LOGITS
    Sticky
    0.45
    umo
    0.44
    在使用
    0.43
     sticky
    0.42
    পেক্ষ
    0.42
    Flags
    0.41
    лын
    0.40
    Berry
    0.40
    作用
    0.39
    CRL
    0.39
    Act Density 0.000%

    No Known Activations