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

    Neuronpedia

    INDEX
    Explanations

    differential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oms
    -0.07
    egend
    -0.07
    ной
    -0.06
    unny
    -0.06
     palindrome
    -0.06
    owan
    -0.06
     إلى
    -0.06
     spinner
    -0.06
     rollout
    -0.06
    .Mesh
    -0.06
    POSITIVE LOGITS
     gusto
    0.07
    이야
    0.06
     �
    0.06
    受
    0.06
     prol
    0.06
     increased
    0.05
    ิย
    0.05
    (percent
    0.05
     hasil
    0.05
    �
    0.05
    Act Density 0.002%

    No Known Activations