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

    Neuronpedia

    INDEX
    Explanations

    names and parentheticals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⣶
    0.43
    addPreferred
    0.42
    DefineConstants
    0.41
    нец
    0.40
     stessa
    0.40
    metto
    0.38
     Directories
    0.38
    نما
    0.37
    进
    0.37
    csproj
    0.37
    POSITIVE LOGITS
     atlas
    0.46
     Atlas
    0.46
     Robert
    0.45
     Juliette
    0.44
     Pamela
    0.42
    Pam
    0.42
    PAM
    0.41
    Robert
    0.41
    iado
    0.40
     pam
    0.39
    Act Density 0.000%

    No Known Activations