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

    Neuronpedia

    INDEX
    Explanations

    on top / stacking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invaded
    -0.07
    عة
    -0.06
    ďte
    -0.06
     banner
    -0.06
     Rigidbody
    -0.06
     Ethiopia
    -0.06
    .report
    -0.06
     rych
    -0.06
     Damage
    -0.06
    (firstName
    -0.06
    POSITIVE LOGITS
    PasswordEncoder
    0.06
     Mayer
    0.06
    declaration
    0.06
    affer
    0.06
    ＿＿＿＿＿＿＿＿
    0.06
     жен
    0.06
    VP
    0.06
    .controllers
    0.06
    autoreleasepool
    0.06
    sein
    0.06
    Act Density 0.025%

    No Known Activations