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

    Neuronpedia

    INDEX
    Explanations

    recipe adjustments or substitutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surrounded
    0.81
     تیار
    0.71
     populated
    0.71
    📅
    0.69
    筵
    0.68
    InProgress
    0.67
    preparation
    0.66
     completed
    0.65
     ঘটতে
    0.65
     futhi
    0.64
    POSITIVE LOGITS
    adjust
    0.92
     substitution
    0.92
     Substitution
    0.89
     adjust
    0.89
     substitutes
    0.88
     Experiment
    0.87
     Substitute
    0.87
     substituted
    0.87
     experiment
    0.87
     substitutions
    0.87
    Act Density 0.183%

    No Known Activations