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

    Neuronpedia

    INDEX
    Explanations

    thesis statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    视角
    0.41
     песни
    0.40
    ধানে
    0.40
    秭
    0.39
    GRESS
    0.38
     হেসে
    0.37
     nicknamed
    0.37
     কাশী
    0.37
    䅞
    0.36
    暱
    0.36
    POSITIVE LOGITS
     statement
    4.13
     statements
    3.81
     Statement
    3.77
    statement
    3.77
    Statement
    3.73
     Statements
    3.52
    statements
    3.44
    Statements
    3.33
     STATEMENT
    3.27
    STATEMENT
    3.14
    Act Density 0.138%

    No Known Activations