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

    Neuronpedia

    INDEX
    Explanations

    power grab disguised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เรา
    0.47
    oine
    0.47
     ambientales
    0.47
    ግር
    0.46
     Steward
    0.45
     indors
    0.45
     искать
    0.44
    firebase
    0.44
     deportes
    0.44
    cesz
    0.44
    POSITIVE LOGITS
     galloping
    0.48
     rotation
    0.46
     pathway
    0.44
     measured
    0.40
     bullies
    0.40
    rentes
    0.40
     certain
    0.40
     sharpened
    0.39
     overtaking
    0.39
     pathways
    0.39
    Act Density 0.000%

    No Known Activations