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

    Neuronpedia

    INDEX
    Explanations

    random number generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৃক
    0.40
     данный
    0.39
    කු
    0.39
    piar
    0.38
    똘
    0.38
    គោ
    0.37
    *$
    0.37
    惱
    0.37
    軗
    0.37
    ishu
    0.36
    POSITIVE LOGITS
     Vent
    0.43
    Vent
    0.37
     Pop
    0.36
     bur
    0.35
     Mé
    0.34
     Independent
    0.34
    olve
    0.34
     flu
    0.33
    MEDI
    0.33
    中心
    0.32
    Act Density 0.001%

    No Known Activations