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

    Neuronpedia

    INDEX
    Explanations

    debunk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iance
    -0.07
    .lst
    -0.06
     opcion
    -0.06
     rollout
    -0.06
    .output
    -0.06
     Hastings
    -0.06
    ldre
    -0.06
    hte
    -0.06
    (dead
    -0.06
     Tut
    -0.06
    POSITIVE LOGITS
     debunk
    0.09
     meth
    0.07
     figuring
    0.07
     searching
    0.07
     overcoming
    0.07
    การส
    0.06
     seab
    0.06
    (Messages
    0.06
     interacting
    0.06
    .vars
    0.06
    Act Density 0.014%

    No Known Activations