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

    Neuronpedia

    INDEX
    Explanations

    Repeating characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    私募
    -0.07
     misogyn
    -0.07
    ikip
    -0.07
     reassure
    -0.07
    乐视
    -0.07
    퓪
    -0.07
     благодар
    -0.06
    _ij
    -0.06
     opcode
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Scheduler
    0.08
    *B
    0.08
    为主的
    0.07
    GST
    0.07
     Movement
    0.07
    REW
    0.07
    _manifest
    0.07
    starter
    0.07
    .Mod
    0.07
    RAFT
    0.07
    Act Density 0.014%

    No Known Activations