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

    Neuronpedia

    INDEX
    Explanations

    worthlessness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	right
    -0.08
    .audio
    -0.07
     Bright
    -0.07
    Good
    -0.07
    REEN
    -0.06
    .RIGHT
    -0.06
     Outline
    -0.06
    Ping
    -0.06
     Boulevard
    -0.06
     Communication
    -0.06
    POSITIVE LOGITS
    に出
    0.07
    ipeg
    0.07
     iş
    0.07
     통
    0.07
    .volume
    0.07
    ,www
    0.07
     İŞ
    0.07
     $_[
    0.06
    �
    0.06
    _arm
    0.06
    Act Density 0.054%

    No Known Activations