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

    Neuronpedia

    INDEX
    Explanations

    state or contextual terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kem
    0.44
     Bond
    0.42
    Kem
    0.41
     sagt
    0.40
     matri
    0.39
     Baj
    0.38
     одна
    0.38
    髪
    0.38
     andet
    0.38
     chemical
    0.37
    POSITIVE LOGITS
    پلز
    0.55
    ho
    0.51
    degrees
    0.51
    idently
    0.51
    ob
    0.49
    pinimg
    0.48
    across
    0.48
    angulo
    0.47
    (__('
    0.47
    za
    0.47
    Act Density 0.001%

    No Known Activations