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

    Neuronpedia

    INDEX
    Explanations

    titles and headlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TP
    -0.06
     Youth
    -0.06
     dgv
    -0.06
    rin
    -0.06
    ingt
    -0.06
     yarat
    -0.06
    _DEFINITION
    -0.06
     rek
    -0.06
     Barrett
    -0.06
     RuntimeMethod
    -0.05
    POSITIVE LOGITS
     apply
    0.07
    되지
    0.07
    .tax
    0.07
    axios
    0.06
    لان
    0.06
    .shutdown
    0.06
    вести
    0.06
    athed
    0.06
    Focus
    0.06
    firm
    0.06
    Act Density 0.060%

    No Known Activations