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

    Neuronpedia

    INDEX
    Explanations

    randomized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .logo
    -0.06
    反
    -0.06
    album
    -0.06
     Provid
    -0.06
    Ingredient
    -0.06
     newsletter
    -0.06
     Vibr
    -0.06
    (expected
    -0.06
     cins
    -0.06
    (error
    -0.06
    POSITIVE LOGITS
     Perm
    0.07
     FSM
    0.06
                    
    0.06
     ViewState
    0.06
    PLOY
    0.06
    atten
    0.06
     искус
    0.06
     Stewart
    0.06
     obtain
    0.06
    OperationContract
    0.06
    Act Density 0.005%

    No Known Activations