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

    Neuronpedia

    INDEX
    Explanations

    overwrite and riding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ACB
    0.38
     punt
    0.38
    ENCY
    0.36
     giãn
    0.36
    ánica
    0.36
    HCM
    0.36
     وفا
    0.35
    obacter
    0.34
    न्ड
    0.34
    ocere
    0.34
    POSITIVE LOGITS
     overwrite
    0.73
     overw
    0.70
    ride
    0.69
    Overwrite
    0.68
     ride
    0.64
    Ride
    0.63
    rides
    0.62
    riding
    0.62
     rides
    0.59
    ridden
    0.59
    Act Density 0.008%

    No Known Activations