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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     belieb
    0.26
    circ
    0.26
    acija
    0.24
    setVisibility
    0.24
     damn
    0.24
    ate
    0.23
    xlim
    0.23
    ensia
    0.23
     savor
    0.23
    x
    0.23
    POSITIVE LOGITS
     If
    0.35
     After
    0.33
     One
    0.32
     Even
    0.32
     Each
    0.32
     Though
    0.32
     Since
    0.31
    If
    0.31
     Everyone
    0.30
     Yet
    0.30
    Act Density 0.000%

    No Known Activations