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

    Neuronpedia

    INDEX
    Explanations

    influential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zusammen
    -0.06
     extensions
    -0.06
    (CONT
    -0.06
     nied
    -0.06
     BITS
    -0.06
     w
    -0.06
     dispatcher
    -0.06
    ns
    -0.06
     Hv
    -0.06
    PhoneNumber
    -0.06
    POSITIVE LOGITS
     influential
    0.35
     Influ
    0.09
     etkili
    0.08
    <stdlib
    0.07
    invisible
    0.07
     hệ
    0.07
    سی
    0.07
    """
↵
↵
    0.07
     Psi
    0.06
    Gesture
    0.06
    Act Density 0.002%

    No Known Activations