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

    Neuronpedia

    INDEX
    Explanations

    Cause/reason conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >manual
    -0.08
    CMD
    -0.07
    ственного
    -0.07
     �
    -0.07
    им
    -0.07
    Vect
    -0.06
    .URI
    -0.06
     Histogram
    -0.06
    -world
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     چون
    0.07
    :↵
    0.07
     Bergen
    0.07
     gay
    0.06
    !↵
    0.06
     flipping
    0.06
     '↵
    0.06
    ]:
↵
    0.06
     adventurer
    0.06
     flip
    0.06
    Act Density 0.022%

    No Known Activations