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

    Neuronpedia

    INDEX
    Explanations

    offers many things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tag
    0.55
    Tagged
    0.52
     parade
    0.51
    Engineer
    0.50
    Isn
    0.50
    phin
    0.50
    Incre
    0.49
     abode
    0.49
    ﻖ
    0.49
    Zombie
    0.49
    POSITIVE LOGITS
     postulated
    0.56
     [['
    0.53
     branched
    0.52
    埸
    0.52
    喤
    0.50
     plt
    0.50
    的地方
    0.48
     hàm
    0.48
     tempat
    0.48
    轪
    0.47
    Act Density 0.004%

    No Known Activations