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

    Neuronpedia

    INDEX
    Explanations

    finds "["

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .exports
    -0.07
    .Interval
    -0.07
    erus
    -0.07
     github
    -0.07
    damage
    -0.07
     healed
    -0.07
    🤚
    -0.07
    ph
    -0.07
    ]';↵
    -0.07
    +xml
    -0.07
    POSITIVE LOGITS
    _green
    0.07
     Sections
    0.07
    一點
    0.07
    _Code
    0.07
     Ziel
    0.06
    unga
    0.06
    _SC
    0.06
    	User
    0.06
    落地
    0.06
    _MIN
    0.06
    Act Density 0.001%

    No Known Activations