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

    Neuronpedia

    INDEX
    Explanations

    say "6 or 12"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _inc
    -0.06
     écrit
    -0.06
     bốn
    -0.06
    	stream
    -0.06
     cardinal
    -0.06
     chan
    -0.06
     roaming
    -0.06
    .classList
    -0.06
     basics
    -0.06
    amburg
    -0.06
    POSITIVE LOGITS
     آزاد
    0.07
     Joh
    0.07
    �
    0.07
    ább
    0.07
    .pick
    0.06
    _GP
    0.06
     solar
    0.06
     Consultants
    0.06
    ificaciones
    0.06
    oje
    0.06
    Act Density 0.015%

    No Known Activations