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

    Neuronpedia

    INDEX
    Explanations

    *R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fak
    -0.07
    ющ
    -0.07
    ouflage
    -0.06
     Helena
    -0.06
    سه
    -0.06
    нів
    -0.06
     �
    -0.06
    �
    -0.06
    ­های
    -0.06
     هم
    -0.06
    POSITIVE LOGITS
     renovation
    0.07
    icana
    0.07
     Ole
    0.06
     majority
    0.06
     *****
    0.06
     Attack
    0.06
     počíta
    0.06
     electron
    0.06
    shader
    0.06
     Criteria
    0.06
    Act Density 0.002%

    No Known Activations