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

    Neuronpedia

    INDEX
    Explanations

    animal experiments and treatments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnityEngine
    -0.07
    alore
    -0.07
    anche
    -0.07
    (Player
    -0.07
     所
    -0.07
    ело
    -0.07
     Пот
    -0.06
     دوست
    -0.06
     wię
    -0.06
    щини
    -0.06
    POSITIVE LOGITS
    .nodes
    0.06
     حرفه
    0.06
    524
    0.06
     nothing
    0.06
     (+
    0.06
    /c
    0.06
    *.
    0.06
    These
    0.06
    肖
    0.06
    136
    0.05
    Act Density 0.046%

    No Known Activations