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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responsiveness
    -0.07
     entail
    -0.06
     став
    -0.06
     superClass
    -0.06
     Wheels
    -0.06
     Baseball
    -0.06
     テ
    -0.06
     Cream
    -0.06
    Then
    -0.06
     profes
    -0.06
    POSITIVE LOGITS
    IRR
    0.08
     illustr
    0.08
     Epidemi
    0.07
    身
    0.07
     epidemi
    0.07
     questionable
    0.07
     тов
    0.06
     dilemma
    0.06
    rollers
    0.06
    ymbols
    0.06
    Act Density 0.000%

    No Known Activations