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

    Neuronpedia

    INDEX
    Explanations

    golang code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    func
    0.50
    덱
    0.43
    funcs
    0.43
    var
    0.43
    িক্ষে
    0.41
    getBody
    0.41
     funcionarios
    0.40
     tcpHeader
    0.39
    ure
    0.39
    }];
    0.39
    POSITIVE LOGITS
     FMT
    0.52
    藤
    0.46
     fmt
    0.44
     FPR
    0.42
    fmt
    0.41
     フォー
    0.41
     Fanny
    0.41
    フォー
    0.40
     Reflect
    0.38
     flag
    0.38
    Act Density 0.005%

    No Known Activations