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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PEN
    -0.07
     Kv
    -0.07
     Concent
    -0.06
    >Contact
    -0.06
     Av
    -0.06
    buie
    -0.06
    orraine
    -0.06
     Piper
    -0.06
    coat
    -0.06
     coherence
    -0.06
    POSITIVE LOGITS
     ability
    0.09
    anced
    0.07
     able
    0.07
     embark
    0.07
     drowning
    0.07
     confer
    0.07
     можлив
    0.06
    ![↵
    0.06
     adept
    0.06
    (Texture
    0.06
    Act Density 0.036%

    No Known Activations