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

    Neuronpedia

    INDEX
    Explanations

    overview and key players

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ጼ
    0.47
     ')[
    0.46
     telas
    0.45
     liberd
    0.45
    𝟘
    0.44
     tecnologias
    0.44
     née
    0.44
     arp
    0.44
     ″
    0.43
     bern
    0.43
    POSITIVE LOGITS
    autions
    0.49
    planung
    0.48
    োনা
    0.46
    ương
    0.46
    可以通过
    0.44
    ニュアル
    0.44
    actic
    0.43
    rierung
    0.43
    mental
    0.43
    可以在
    0.42
    Act Density 0.005%

    No Known Activations