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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utter
    -0.06
     Attachment
    -0.06
     surround
    -0.06
    .Require
    -0.06
     admissions
    -0.06
    ifton
    -0.06
    щее
    -0.06
     Interracial
    -0.06
     brilliant
    -0.06
    арам
    -0.06
    POSITIVE LOGITS
    Policy
    0.08
    ï
    0.08
    policy
    0.08
    ovic
    0.07
    .tax
    0.07
     превыш
    0.07
     hij
    0.07
     policy
    0.07
     impover
    0.07
    дап
    0.07
    Act Density 0.005%

    No Known Activations