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

    Neuronpedia

    INDEX
    Explanations

    compared to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deprecated
    0.73
     foi
    0.68
     unsatisfactory
    0.68
     ineffective
    0.67
     undesired
    0.67
     erroneous
    0.66
     being
    0.66
     deja
    0.64
     undesirable
    0.64
     been
    0.63
    POSITIVE LOGITS
    Bus
    0.62
    Club
    0.59
    Vent
    0.59
    Car
    0.57
    Pen
    0.56
    gameObjects
    0.56
    Am
    0.55
    ventures
    0.55
    Mor
    0.55
    Memorial
    0.55
    Act Density 0.244%

    No Known Activations