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

    Neuronpedia

    INDEX
    Explanations

    experiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ine
    1.24
    のではない
    1.20
    ри
    1.15
    ｽ
    1.08
     presence
    1.07
     simulation
    1.07
    스를
    1.07
    ﻳ
    1.06
    亠
    1.05
    үүн
    1.04
    POSITIVE LOGITS
    move
    1.77
    nummer
    1.55
    larni
    1.53
    larda
    1.48
    ர்
    1.47
    lari
    1.46
    ாக
    1.45
    niveau
    1.42
    machen
    1.41
    น
    1.41
    Act Density 0.013%

    No Known Activations