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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    在
    -0.07
     Through
    -0.06
     Jinping
    -0.06
    iotic
    -0.06
     divisor
    -0.06
     symp
    -0.06
    figures
    -0.06
    imal
    -0.06
    르는
    -0.06
     through
    -0.06
    POSITIVE LOGITS
    �n
    0.07
    /server
    0.07
    akeup
    0.07
    unlink
    0.06
    _php
    0.06
     доме
    0.06
     trois
    0.06
     Hawkins
    0.06
     sağlamak
    0.06
    Bug
    0.06
    Act Density 0.016%

    No Known Activations