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

    Neuronpedia

    INDEX
    Explanations

    lists of attributes and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ava
    0.96
     Are
    0.91
     Audubon
    0.91
     ANG
    0.91
                    
    0.90
     AE
    0.89
     Aj
    0.88
     Aga
    0.86
     Animal
    0.86
     Av
    0.85
    POSITIVE LOGITS
    Pherson
    0.71
    alloc
    0.69
    eqn
    0.69
    steuerung
    0.68
    ﺰ
    0.68
    >&
    0.68
    рга
    0.64
    ared
    0.64
    esterno
    0.63
    ương
    0.63
    Act Density 0.129%

    No Known Activations