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

    Neuronpedia

    INDEX
    Explanations

    commands and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erdere
    0.60
     Ա
    0.56
     මෙම
    0.56
     ทีม
    0.54
     व्हाउचर
    0.53
    ₍
    0.53
     matchup
    0.52
    Ꮰ
    0.52
    𝙾
    0.52
    ”،
    0.51
    POSITIVE LOGITS
     psychotherapy
    0.41
     religious
    0.40
     symbolic
    0.39
     constitutive
    0.39
     political
    0.36
     child
    0.35
     poets
    0.35
     children
    0.35
     speech
    0.35
    1
    0.34
    Act Density 0.000%

    No Known Activations