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

    Neuronpedia

    INDEX
    Explanations

    code or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revital
    0.45
     virtual
    0.41
     trio
    0.40
     Whi
    0.39
     sensational
    0.39
     inter
    0.39
     robo
    0.38
     monstrous
    0.38
     couple
    0.37
     hum
    0.37
    POSITIVE LOGITS
    usize
    0.50
    ()/
    0.50
    ())
    0.49
    
    0.48
    ()).
    0.47
    __()
    0.44
    ฯ
    0.44
    ()),
    0.43
    ()-
    0.43
    -
    0.43
    Act Density 4.660%

    No Known Activations