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

    Neuronpedia

    INDEX
    Explanations

    proper English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grazed
    0.38
    MovementControls
    0.38
    ᷅
    0.37
     ordinairement
    0.36
     reactant
    0.36
     कंटिन
    0.35
     oxides
    0.35
    ())+
    0.35
     insufficiency
    0.35
    㠃
    0.34
    POSITIVE LOGITS
     To
    0.57
    To
    0.55
    to
    0.49
     to
    0.47
    并
    0.44
    Edit
    0.44
    setClass
    0.41
    edit
    0.41
    並
    0.41
     Son
    0.40
    Act Density 0.000%

    No Known Activations