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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /R
    -0.08
     repl
    -0.07
     ISP
    -0.06
     Regents
    -0.06
     Approach
    -0.06
     FAG
    -0.06
    맥
    -0.06
    (robot
    -0.06
    abs
    -0.06
     collaborate
    -0.06
    POSITIVE LOGITS
    pipe
    0.07
    /code
    0.07
     _$
    0.07
     localhost
    0.07
    _schedule
    0.06
     Cornwall
    0.06
     money
    0.06
    Με
    0.06
    _Test
    0.06
    _account
    0.06
    Act Density 0.008%

    No Known Activations