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

    Neuronpedia

    INDEX
    Explanations

    simultaneously, before, plus, hijacking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    use
    0.50
    କ
    0.48
    OOSE
    0.48
    まず
    0.46
    務
    0.46
     initially
    0.46
    ート
    0.45
    addUser
    0.45
    lcii
    0.45
    Ꮄ
    0.45
    POSITIVE LOGITS
     혹은
    0.49
     makna
    0.45
     또는
    0.45
     zahr
    0.44
     omkring
    0.44
     Skyl
    0.44
     அல்லது
    0.43
     Counseling
    0.43
     করিতেছি
    0.43
     olan
    0.42
    Act Density 0.002%

    No Known Activations