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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    man
    -0.08
    EE
    -0.08
    co
    -0.07
    6
    -0.07
    w
    -0.07
    bo
    -0.07
    Z
    -0.07
    8
    -0.07
    we
    -0.07
    _ra
    -0.07
    POSITIVE LOGITS
     противоп
    0.07
     />";↵
    0.07
     ")
↵
    0.07
    イト
    0.07
     courthouse
    0.06
     ]
    0.06
    _AGENT
    0.06
    TECT
    0.06
     Eternal
    0.06
    ुध
    0.06
    Act Density 0.048%

    No Known Activations