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

    Neuronpedia

    INDEX
    Explanations

    repetition and routines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRA
    -0.31
    è¡Įä¸ļåıijå±ķ
    -0.27
    HOLDER
    -0.27
    contre
    -0.27
    ewolf
    -0.26
    fffffff
    -0.26
    REW
    -0.25
    enga
    -0.25
    OTES
    -0.25
    ffffff
    -0.25
    POSITIVE LOGITS
    limited
    0.30
     repeating
    0.28
    رد
    0.27
    mdl
    0.26
     static
    0.25
    vide
    0.25
    ¦
    0.25
    åĽºå®ļ
    0.24
    mit
    0.24
    /static
    0.24
    Act Density 2.004%

    No Known Activations