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

    Neuronpedia

    INDEX
    Explanations

    power management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Midnight
    0.42
    হার
    0.40
     bedre
    0.39
    valids
    0.38
    䡈
    0.38
     ближе
    0.38
    炵
    0.37
    𝑖
    0.37
    湟
    0.37
    ături
    0.36
    POSITIVE LOGITS
     Specifically
    0.46
     Specifies
    0.42
     But
    0.42
     Func
    0.40
     Jun
    0.38
     Sep
    0.37
     c
    0.37
     code
    0.37
    Reuters
    0.37
     Intu
    0.37
    Act Density 0.001%

    No Known Activations