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

    Neuronpedia

    INDEX
    Explanations

    comment endings in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    public function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.68
    stylers
    -0.59
     autorytatywna
    -0.58
     ModelRenderer
    -0.58
    EndProject
    -0.55
    WriteBarrier
    -0.55
     queſta
    -0.55
     sumpay
    -0.55
    BufferException
    -0.54
     useAuth
    -0.54
    POSITIVE LOGITS
    ↵↵
    0.46
    ↵↵↵↵
    0.45
    ↵↵↵
    0.38
    ↵↵↵↵↵↵↵
    0.37
    ↵↵↵↵↵↵
    0.35
    Jack
    0.33
    Black
    0.33
    ↵↵↵↵↵
    0.33
    ↵↵↵↵↵↵↵↵
    0.33
    public
    0.33
    Act Density 0.004%

    No Known Activations