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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ultural
    -0.07
    iphertext
    -0.07
     Museum
    -0.06
    Pal
    -0.06
     stationary
    -0.06
     refugees
    -0.06
     matt
    -0.06
     unm
    -0.06
    并
    -0.06
    ancy
    -0.06
    POSITIVE LOGITS
    's
    0.08
    ’s
    0.08
     vanished
    0.06
     greatness
    0.06
     نشر
    0.06
     strpos
    0.06
     заст
    0.06
    Quaternion
    0.06
     vant
    0.06
     которого
    0.06
    Act Density 0.029%

    No Known Activations