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

    Neuronpedia

    INDEX
    Explanations

    special characters in text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceded
    0.41
     Purpose
    0.37
    aced
    0.37
     인한
    0.36
    টিশ
    0.36
     နောက်
    0.36
     amended
    0.35
    monton
    0.35
    ក
    0.35
    ond
    0.35
    POSITIVE LOGITS
    estr
    0.42
     manej
    0.37
     gotten
    0.36
    コマンド
    0.36
    语音
    0.36
     வைத்திருக்க
    0.35
     മത്സ്യ
    0.35
    ிலி
    0.35
     deadly
    0.35
     bicicletas
    0.35
    Act Density 0.166%

    No Known Activations