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

    Neuronpedia

    INDEX
    Explanations

    vestib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вже
    -0.07
     دوباره
    -0.07
    θενής
    -0.07
    �
    -0.07
    �
    -0.06
     compartir
    -0.06
    iembre
    -0.06
    法人
    -0.06
     deficiencies
    -0.06
     जगह
    -0.06
    POSITIVE LOGITS
    _close
    0.06
     Ronald
    0.06
    OLON
    0.06
    _o
    0.06
    having
    0.06
     o
    0.06
     adore
    0.06
     OR
    0.06
     champs
    0.06
     travers
    0.06
    Act Density 0.013%

    No Known Activations