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

    Neuronpedia

    INDEX
    Explanations

    schemas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дорож
    -0.07
     erection
    -0.07
    ----------
    -0.07
     rus
    -0.07
     village
    -0.07
     чер
    -0.07
     женщина
    -0.06
     Zah
    -0.06
     sir
    -0.06
     Brut
    -0.06
    POSITIVE LOGITS
     clone
    0.06
    andır
    0.06
    X
    0.06
    DOWN
    0.06
    PLEX
    0.06
     παρα
    0.06
     슬
    0.06
    -rate
    0.06
    -sales
    0.06
     профессиональ
    0.05
    Act Density 0.001%

    No Known Activations