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

    Neuronpedia

    INDEX
    Explanations

    rather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    undai
    -0.08
    oui
    -0.08
    conde
    -0.08
    dız
    -0.07
    763
    -0.07
    PI
    -0.07
    mie
    -0.07
    UIScreen
    -0.07
    unnable
    -0.07
    opoulos
    -0.07
    POSITIVE LOGITS
     rather
    0.16
    rather
    0.15
     Rather
    0.13
    Rather
    0.11
    ather
    0.09
     rh
    0.08
     الر
    0.08
    ER
    0.08
     fairly
    0.07
    Far
    0.07
    Act Density 0.010%

    No Known Activations