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

    Neuronpedia

    INDEX
    Explanations

    Blog posts/social media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ability
    -0.07
     '::
    -0.07
     exploration
    -0.06
    Ability
    -0.06
    $sub
    -0.06
     glanced
    -0.06
     CV
    -0.06
    ssh
    -0.06
     rightful
    -0.06
     MANUAL
    -0.06
    POSITIVE LOGITS
    ramework
    0.07
    .Design
    0.07
    atego
    0.07
    .endDate
    0.07
    五月
    0.06
    errorMessage
    0.06
    еж
    0.06
     unterschied
    0.06
    .titleLabel
    0.06
    (commands
    0.06
    Act Density 0.056%

    No Known Activations