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

    Neuronpedia

    INDEX
    Explanations

    Options

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    setup
    -0.07
    .aspect
    -0.07
     remarkably
    -0.07
    sen
    -0.06
    Operand
    -0.06
     Bit
    -0.06
    ptoms
    -0.06
    Something
    -0.06
    no
    -0.06
    首届
    -0.06
    POSITIVE LOGITS
     hookers
    0.07
    Authorize
    0.07
    🎤
    0.07
    (\'
    0.07
    𝘔
    0.07
    NGTH
    0.07
    Cooldown
    0.06
    ("#{
    0.06
    姆
    0.06
    .writer
    0.06
    Act Density 0.002%

    No Known Activations