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

    Neuronpedia

    INDEX
    Explanations

    code snippets or URLs

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fácil
    -0.45
    ">{{$
    -0.42
    ="{{$
    -0.42
    }])
    -0.42
     UIApplication
    -0.41
    ✭
    -0.41
    assin
    -0.40
    }}=$
    -0.40
    !');
    -0.39
    +");
    -0.38
    POSITIVE LOGITS
    SourceChecksum
    0.79
    InstanceState
    0.77
     estekak
    0.69
    PerformLayout
    0.67
    UserScript
    0.65
     nakalista
    0.65
    StandardCharsets
    0.64
     noDo
    0.63
    providedIn
    0.63
    modb
    0.63
    Act Density 0.079%

    No Known Activations