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

    Neuronpedia

    INDEX
    Explanations

    , td structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ('');
    0.39
     ②
    0.39
     narrowly
    0.38
    Maximum
    0.37
    سون
    0.37
    <<<<
    0.36
    کو
    0.36
    Indust
    0.35
    ców
    0.35
    minimal
    0.34
    POSITIVE LOGITS
     ఇతర
    0.42
    选手
    0.40
    以下的
    0.39
     factores
    0.38
     которыми
    0.38
    ETE
    0.38
     ಇತರ
    0.37
     Pad
    0.37
     ஆகியோர்
    0.36
     analisi
    0.36
    Act Density 0.001%

    No Known Activations