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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     schema
    -0.07
     ifade
    -0.07
     magnet
    -0.07
    ُو
    -0.06
     anonymous
    -0.06
    ushman
    -0.06
     existential
    -0.06
    /dom
    -0.06
    -described
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    \"",↵
    0.08
    jící
    0.08
    드
    0.07
     پیش
    0.07
     newList
    0.07
    ple
    0.06
     [],↵
    0.06
    HEEL
    0.06
    )")
    0.06
     beasts
    0.06
    Act Density 0.000%

    No Known Activations