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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to direction and changes in direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    new direction or future path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ----</
    -0.42
    يكب
    -0.41
    utri
    -0.41
    libft
    -0.41
    HttpPut
    -0.38
    исленность
    -0.38
    Чу
    -0.38
    orti
    -0.38
    enci
    -0.38
     Hamma
    -0.37
    POSITIVE LOGITS
     direction
    2.38
     directions
    1.92
    direction
    1.90
     Direction
    1.80
    方向
    1.76
     DIRECTION
    1.70
    的方向
    1.65
    Direction
    1.65
    directions
    1.53
     direzione
    1.51
    Act Density 0.101%

    No Known Activations